Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Top-k accuracy - Add support for multilabel/multioutput cases #16666

Open
gbolmier opened this issue Mar 10, 2020 · 1 comment
Open

Top-k accuracy - Add support for multilabel/multioutput cases #16666

gbolmier opened this issue Mar 10, 2020 · 1 comment
Labels
module:metrics Needs Decision Requires decision New Feature

Comments

@gbolmier
Copy link
Contributor

gbolmier commented Mar 10, 2020 •
edited

Describe the workflow you want to enable

Add support for multilabel/multioutput top-k accuracy. Multiclass setting being implemented here #16625

Additional context

  • Some multilabel classifiers treat each label independently, when it's the case does it make sense to rank independent predicted scores?

  • Multioutput-multiclass approach treats each output as a multiclass problem, therefore we could consider an answer for a sample as correct when all outputs are correct.
@gbolmier gbolmier mentioned this issue Mar 10, 2020
Merged
@TakashiMatsuda TakashiMatsuda mentioned this issue Nov 19, 2021
Closed
@TakashiMatsuda
Copy link

@cmarmo @gbolmier
I tried to implement the multilabel-indicator case.
#21710

I will complete the PR If this metric is wanted.
Do you need this metric?( I'll close it if it is not needed.)

@cmarmo cmarmo added the Needs Decision Requires decision label Nov 19, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
module:metrics Needs Decision Requires decision New Feature
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

[WIP] Top k accuracy multilabel indicator TakashiMatsuda/scikit-learn
3 participants
@TakashiMatsuda @cmarmo @gbolmier